Upload new k-quant GGML quantised models.
Browse files
llama-7b.ggmlv3.q4_K_M.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2ea51ffa5e467535e9096d95727e5b6a262eadff963d2e95ab28120c4ee2720
|
| 3 |
+
size 4046922368
|